# Personal Attribute Prediction from Conversations

arXiv: https://arxiv.org/abs/2209.09619 · HTML: https://mlsanity.com/paper/2209.09619/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 19 references that are in the map.
- First posted on arXiv 29 Aug 2022.

## Builds on (most cited first, 5 of 5)

- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [End-to-End Neural Ad-hoc Ranking with Kernel Pooling](https://mlsanity.com/paper/1706.06613/) (2017)
- [Text Classification Using Label Names Only: A Language Model Self-Training Approach](https://mlsanity.com/paper/2010.07245/) (2020)
- [Listening between the Lines: Learning Personal Attributes from Conversations](https://mlsanity.com/paper/1904.10887/) (2019)
- [N-GrAM: New Groningen Author-profiling Model](https://mlsanity.com/paper/1707.03764/) (2017)

## Built on by (most cited first, 3 of 3)

- [Representation Learning for Person or Entity-centric Knowledge Graphs: An Application in Healthcare](https://mlsanity.com/paper/2305.05640/) (2023)
- [Low-resource Personal Attribute Prediction from Conversation](https://mlsanity.com/paper/2211.15324/) (2022)
- [DiagLink: A Dual-User Diagnostic Assistance System by Synergizing Experts with LLMs and Knowledge Graphs](https://mlsanity.com/paper/2601.20311/) (2026)

## Abstract (arXiv)

Personal knowledge bases (PKBs) are critical to many applications, such as Web-based chatbots and personalized recommendation. Conversations containing rich personal knowledge can be regarded as a main source to populate the PKB. Given a user, a user attribute, and user utterances from a conversational system, we aim to predict the personal attribute value for the user, which is helpful for the enrichment of PKBs. However, there are three issues existing in previous studies: (1) manually labeled utterances are required for model training; (2) personal attribute knowledge embedded in both utterances and external resources is underutilized; (3) the performance on predicting some difficult personal attributes is unsatisfactory. In this paper, we propose a framework DSCGN based on the pre-trained language model with a noise-robust loss function to predict personal attributes from conversations without requiring any labeled utterances. We yield two categories of supervision, i.e., document-level supervision via a distant supervision strategy and contextualized word-level supervision via a label guessing method, by mining the personal attribute knowledge embedded in both unlabeled utterances and external resources to fine-tune the language model. Extensive experiments over two real-world data sets (i.e., a profession data set and a hobby data set) show our framework obtains the best performance compared with all the twelve baselines in terms of nDCG and MRR.